User profiles for Shin Ishii
Shin IshiiKyoto University Verified email at i.kyoto-u.ac.jp Cited by 12490 |
Virtual adversarial training: a regularization method for supervised and semi-supervised learning
We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …
A critical time window for dopamine actions on the structural plasticity of dendritic spines
…, GCR Ellis-Davies, H Urakubo, S Ishii… - Science, 2014 - science.org
Animal behaviors are reinforced by subsequent rewards following within a narrow time
window. Such reward signals are primarily coded by dopamine, which modulates the synaptic …
window. Such reward signals are primarily coded by dopamine, which modulates the synaptic …
A Bayesian missing value estimation method for gene expression profile data
…, I Takemasa, M Monden, K Matsubara, S Ishii - …, 2003 - academic.oup.com
Motivation: Gene expression profile analyses have been used in numerous studies covering
a broad range of areas in biology. When unreliable measurements are excluded, missing …
a broad range of areas in biology. When unreliable measurements are excluded, missing …
Control of exploitation–exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been
an important issue. This paper presents a new method that controls the balance between …
an important issue. This paper presents a new method that controls the balance between …
Dopamine D2 receptors in discrimination learning and spine enlargement
Y Iino, T Sawada, K Yamaguchi, M Tajiri, S Ishii… - Nature, 2020 - nature.com
Dopamine D2 receptors (D2Rs) are densely expressed in the striatum and have been
linked to neuropsychiatric disorders such as schizophrenia 1 , 2 . High-affinity binding of …
linked to neuropsychiatric disorders such as schizophrenia 1 , 2 . High-affinity binding of …
Distributional smoothing with virtual adversarial training
We propose local distributional smoothness (LDS), a new notion of smoothness for statistical
model that can be used as a regularization term to promote the smoothness of the model …
model that can be used as a regularization term to promote the smoothness of the model …
On-line EM algorithm for the normalized Gaussian network
M Sato, S Ishii - Neural computation, 2000 - ieeexplore.ieee.org
… Masa-aki Sato and Shin Ishii … Our method can also be applied to reinforcement
learning (Sato & Ishii, 1999) and the reconstruction of nonlinear dynamics (Ishii & Sato, 1998). …
learning (Sato & Ishii, 1999) and the reconstruction of nonlinear dynamics (Ishii & Sato, 1998). …
Frontal affinity chromatography: theory for its application to studies on specific interactions of biomolecules
KI Kasai, Y Oda, M Nishikata, SI Ishii - Journal of Chromatography B …, 1986 - Elsevier
Affinity chromatography is very useful in the investigation and characterization of specific
interaction between biomolecules. Frontal analysis in affinity chromatography is advantageous …
interaction between biomolecules. Frontal analysis in affinity chromatography is advantageous …
Learning a common dictionary for subject-transfer decoding with resting calibration
Brain signals measured over a series of experiments have inherent variability because of
different physical and mental conditions among multiple subjects and sessions. Such …
different physical and mental conditions among multiple subjects and sessions. Such …
[HTML][HTML] Resolution of uncertainty in prefrontal cortex
Making optimal decisions in the face of uncertain or incomplete information arises as a
common problem in everyday behavior, but the neural processes underlying this ability remain …
common problem in everyday behavior, but the neural processes underlying this ability remain …